Sponsored by Deepsite.site

Tag

#typescript

425 results found

Agent Smith

Auto-generate AGENTS.md from your codebase Stop writing AGENTS.md by hand. Run agentsmith and it scans your codebase to generate a comprehensive context file that AI coding tools read automatically. What is AGENTS.md? AGENTS.md is an open standard for giving AI coding assistants context about your project. It's adopted by 60,000+ projects and supported by: Cursor GitHub Copilot Claude Code VS Code Gemini CLI And 20+ more tools AI tools automatically discover and read AGENTS.md files - no configuration needed. What agentsmith does Instead of writing AGENTS.md manually, agentsmith scans your codebase and generates it: npx @jpoindexter/agent-smith agentsmith Scanning /Users/you/my-project... ✓ Found 279 components ✓ Found 5 components with CVA variants ✓ Found 37 color tokens ✓ Found 14 custom hooks ✓ Found 46 API routes (8 with schemas) ✓ Found 87 environment variables ✓ Detected Next.js (App Router) ✓ Detected shadcn/ui (26 Radix packages) ✓ Found cn() utility ✓ Found mode/design-system ✓ Detected 6 code patterns ✓ Found existing CLAUDE.md ✓ Found .ai/ folder (12 files) ✓ Found prisma schema (28 models) ✓ Scanned 1572 files (11.0 MB, 365,599 lines) ✓ Found 17 barrel exports ✓ Found 15 hub files (most imported) ✓ Found 20 Props types ✓ Found 40 test files (12% component coverage) ✓ Generated AGENTS.md ~11K tokens (9% of 128K context) Install # Run directly (no install needed) npx @jpoindexter/agent-smith # Or install globally npm install -g @jpoindexter/agent-smith Usage # Generate AGENTS.md in current directory agentsmith # Generate for a specific directory agentsmith ./my-project # Preview without writing (dry run) agentsmith --dry-run # Custom output file agentsmith --output CONTEXT.md # Force overwrite existing file agentsmith --force Output Modes # Default - comprehensive output (~11K tokens) agentsmith # Compact - fewer details (~20% smaller) agentsmith --compact # Compress - signatures only (~40% smaller) agentsmith --compress # Minimal - ultra-compact (~3K tokens) agentsmith --minimal # XML format (industry standard, matches Repomix) agentsmith --xml # Include file tree visualization agentsmith --tree

MCP-MESSENGER

**SlashMCP** is a production-grade AI workspace that connects LLMs to real-world data and tools through an intuitive chat interface. Built on the Model Context Protocol (MCP), it enables seamless interaction with multiple AI providers (OpenAI, Claude, Gemini) while providing powerful capabilities for document analysis, financial data queries, web scraping, and multi-agent workflow orchestration. ### Key Features: - **Multi-LLM Support**: Switch between GPT-4, Claude, and Gemini at runtime—no restart needed - **Smart Command Autocomplete**: Type `/` to discover and execute MCP server commands instantly - **Document Intelligence**: Drag-and-drop documents with automatic OCR extraction and vision analysis - **Financial Data Integration**: Real-time stock quotes, charts, and prediction market data via Alpha Vantage and Polymarket - **Browser Automation**: Web scraping and navigation using Playwright MCP - **Multi-Agent Orchestration**: Intelligent routing with specialized agents for command discovery, tool execution, and response synthesis - **Dynamic MCP Registry**: Add and use any MCP server on the fly without code changes - **Voice Interaction**: Browser-based transcription and text-to-speech support ### Use Cases: - Research and analysis workflows - Document processing and extraction - Financial market monitoring - Web data collection and comparison - Multi-step task automation **Live Demo:** [ slashmcp.vercel.app ]( https://slashmcp.vercel.app ) **GitHub:** [ github.com/mcpmessenger/slashmcp ]( https://github.com/mcpmessenger/slashmcp ) **Website:** [ slashmcp.com](https://slashmcp.com )